gvc_opentargets

Setup environment

library(tidyverse)
library(ggformula)
library(janitor)
library(skimr)
library(broom)
library(readxl)
library(jsonlite)

theme_set(theme_bw())

set.seed(666)

Read and prep data

Genes within 1Mb window of GVC loci:

gvc <- read_xlsx("GVC_1Mb_comparison_050224.xlsx") |>
  clean_names() |> 
  separate(gene_id, c("gene_id", "version")) |>
  select(-version, -agora_nominated_list, -opentarget_info)

gvc

Gene prioritization scores from Agora https://www.synapse.org/Synapse:syn25741025:

ago <- read_json("syn25741025.overall_scores.json", simplifyVector = TRUE) |> as_tibble()

ago

sum(gvc$gene_id %in% ago$ensembl_gene_id)

[1] 2248

sum(gvc$gene_symbol %in% ago$hgnc_symbol)

[1] 2234

Genes from Open Targets:

ot <- read_tsv("OT-MONDO_0004975-associated-targets-5_4_2024-v24_03.tsv", show_col_types = FALSE)

ot

sum(ot$symbol %notin% ago$hgnc_symbol)

[1] 293

library(gprofiler2)

otcols <- colnames(ot)
otensg <- gconvert(
  query = ot$symbol,
  organism = "hsapiens",
  target= "ENSG",
  mthreshold = Inf,
  filter_na = TRUE) |> 
  mutate(input_number = as.character(input_number)) |>
  left_join(ot |> rownames_to_column(var = "input_number"), by = "input_number") |> 
  select(ensembl_gene_id = target, otcols)

otensg

d <- gvc |>
  left_join(ago, by = join_by(gene_id == ensembl_gene_id)) |> 
  left_join(otensg, by = join_by(gene_id == ensembl_gene_id)) |> 
  arrange(desc(globalScore))

d

skim(d)

Data summary

Name	d
Number of rows	2473
Number of columns	61
_______________________
Column type frequency:
character	51
numeric	10
________________________
Group variables	None

Variable type: character

skim_variable	n_missing	complete_rate	min	max	empty	n_unique	whitespace
grouped_loci_rs_id_gvc	0	1.00	6	11	0	146	0
grouped_loci_gvc	0	1.00	3	43	0	84	0
chrom	0	1.00	4	5	0	21	0
rsid	0	1.00	6	11	0	146	0
ref	0	1.00	1	1	0	4	0
alt	0	1.00	1	5	0	14	0
gene_id	0	1.00	15	15	0	1344	0
gene_strand	0	1.00	1	1	0	2	0
gene_symbol	0	1.00	3	14	0	1344	0
gene_type	0	1.00	14	14	0	1	0
hgnc_symbol	221	0.91	3	14	0	1212	0
symbol	1649	0.33	3	11	0	404	0
otGeneticsPortal	1649	0.33	7	20	0	196	0
geneBurden	1649	0.33	7	7	0	1	0
eva	1649	0.33	1	19	0	9	0
genomicsEngland	1649	0.33	7	18	0	4	0
gene2Phenotype	1649	0.33	7	7	0	1	0
uniprotLiterature	1649	0.33	7	18	0	3	0
uniprotVariants	1649	0.33	7	18	0	3	0
orphanet	1649	0.33	7	17	0	2	0
clingen	1649	0.33	7	7	0	1	0
cancerGeneCensus	1649	0.33	7	7	0	1	0
intogen	1649	0.33	7	7	0	1	0
evaSomatic	1649	0.33	7	7	0	1	0
cancerBiomarkers	1649	0.33	7	7	0	1	0
chembl	1649	0.33	7	19	0	14	0
crisprScreen	1649	0.33	7	19	0	41	0
crispr	1649	0.33	7	7	0	1	0
slapenrich	1649	0.33	7	7	0	1	0
progeny	1649	0.33	7	7	0	1	0
reactome	1649	0.33	7	17	0	2	0
sysbio	1649	0.33	7	19	0	2	0
europepmc	1649	0.33	7	20	0	43	0
expressionAtlas	1649	0.33	7	20	0	173	0
impc	1649	0.33	7	19	0	7	0
maxClinicalTrialPhase	1649	0.33	1	7	0	4	0
isInMembrane	1649	0.33	1	7	0	3	0
isSecreted	1649	0.33	1	7	0	3	0
hasLigand	1649	0.33	1	7	0	3	0
hasSmallMoleculeBinder	1649	0.33	1	7	0	3	0
hasPocket	1649	0.33	1	7	0	3	0
mouseOrthologMaxIdentityPercentage	1649	0.33	1	20	0	272	0
hasHighQualityChemicalProbes	1649	0.33	1	7	0	3	0
geneticConstraint	1649	0.33	7	22	0	403	0
mouseKoScore	1649	0.33	1	21	0	230	0
geneEssentiality	1649	0.33	1	7	0	3	0
hasSafetyEvent	1649	0.33	2	7	0	2	0
isCancerDriverGene	1649	0.33	2	7	0	2	0
paralogMaxIdentityPercentage	1649	0.33	1	21	0	73	0
tissueSpecificity	1649	0.33	1	7	0	5	0
tissueDistribution	1649	0.33	1	7	0	5	0

Variable type: numeric

skim_variable	n_missing	complete_rate	mean	sd	p0	p25	p50	p75	p100	hist
chrom_start	0	1.00	62436245.64	48374178.54	413333.00	31121778.00	51224705.00	94979791.00	233173930.00	▇▆▂▂▁
chrom_end	0	1.00	62436246.64	48374178.54	413334.00	31121779.00	51224706.00	94979792.00	233173931.00	▇▆▂▂▁
distance	0	1.00	12719.87	278764.16	-499286.00	-218912.00	14939.00	241039.00	499987.00	▆▇▇▇▇
absolute_distance	0	1.00	238261.90	145188.23	114.00	115708.00	229173.00	361466.00	499987.00	▇▇▇▇▆
gene_start	0	1.00	62406168.65	48373400.00	87249.00	31131432.00	50825288.00	95244912.00	233671897.00	▇▆▂▂▁
gene_end	0	1.00	62440568.15	48376158.70	97094.00	31135727.00	50837213.00	95269201.00	233773300.00	▇▆▂▂▁
target_risk_score	221	0.91	2.46	0.99	0.57	1.57	2.44	3.34	4.71	▆▇▇▇▂
genetics_score	221	0.91	1.66	0.46	0.57	1.28	1.64	2.00	2.90	▂▇▇▆▁
multi_omics_score	465	0.81	0.90	0.76	0.00	0.00	1.01	1.54	2.00	▇▂▂▅▅
globalScore	1649	0.33	0.13	0.16	0.00	0.01	0.06	0.23	0.84	▇▂▁▁▁

query <- ot |> arrange(desc(globalScore)) |> distinct(symbol) |> pull(symbol)

gostres <- gost(query = query,
                organism = "hsapiens",
                domain_scope = "annotated",
                exclude_iea = TRUE,
                ordered_query = TRUE,
                significant = TRUE,
                user_threshold = 0.005,
                correction_method = "fdr")

gostres$result

gostplot(gostres, capped = FALSE, interactive = TRUE)

otensg |>
  left_join(ago, by = "ensembl_gene_id") |>
  slice_max(globalScore, n = 100) |>
  select(ensembl_gene_id, symbol, globalScore, target_risk_score, genetics_score, multi_omics_score) |>
  drop_na(globalScore, target_risk_score) |>
  summarize(cor = tidy(cor.test(globalScore, target_risk_score, method="spearman"))) |>
  unnest(cor)